Method for real-time online temperature distribution monitoring of GIL, and related apparatus

Abstract

A method for real-time online temperature distribution monitoring of a GIL and a related apparatus, which relate to the technical field of electric power. The method comprises: building a GIL simulation model, and determining variables that affect the overall temperature distribution of a GIL and determining monitoring point positions; determining selection ranges of the variables, acquiring a data set containing the variables and a temperature field data set, and exporting same; extracting a monitoring point temperature data set and a solid-domain temperature data set from a temperature data set, and performing dimensionality reduction on the solid-domain temperature data set; establishing an implicit nonlinear relationship between the monitoring point temperature data set and the low-dimensional data set, so as to obtain a computational model of an overall temperature solid domain portion of the GIL, and establishing a mapping relationship between the solid-domain temperature data set and the temperature field data set, so as to obtain an overall temperature online monitoring model of the GIL; and inputting a monitoring point temperature into said monitoring model to obtain an overall solid-domain temperature distribution of the GIL, and reconstructing the overall temperature distribution of the GIL by means of the monitoring model. Therefore, the present invention solves the problem of incapability of monitoring internal states of GIL apparatuses in real time.

Description

Real-time online monitoring method for GIL temperature distribution and related device

[0001] The present application claims priority to the Chinese patent application No. 202410631576.1, filed on May 21, 2024, and entitled "Real-time online monitoring method for GIL temperature distribution and related device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of electric power, and in particular to a real-time online monitoring method for GIL temperature distribution and related device. BACKGROUND

[0003] Gas insulated transmission line (GIL) has been widely used in power systems. GIL has a long length, large power transmission capacity, and a fully enclosed structure, which leads to high internal heating risk and complexity. In particular, for the contact resistance position of the GIL current-carrying conductor, the volume is small and the flow capacity is large. Local overheating caused by poor contact can lead to a decrease in the insulation performance of the GIL, and even cause a short circuit fault.

[0004] Currently, the main methods for monitoring the operating temperature of GIL are indirect temperature measurement based on the shell and non-contact infrared temperature measurement of the conductor. However, the above methods can only provide GIL thermal fault state identification and positioning, and cannot provide accurate internal temperature information. Although simulation calculation can obtain device internal temperature field data, current methods mainly use finite element simulation software such as ANSYS and COMSOL, which consume a large amount of time and are difficult to achieve rapid calculation and real-time monitoring in actual applications, and cannot meet the needs of digital real-time evaluation and analysis of power equipment. Therefore, in order to solve the problem of obtaining the internal temperature field of GIL in real time using limited external measurement data, it is necessary to further develop a data-driven temperature field real-time calculation method to realize real-time state monitoring of the overall temperature field of the GIL internal overslip contact.

[0005] SUMMARY

[0006] The present application provides a real-time online monitoring method for GIL temperature distribution and related device, which solves the problem that three-phase integrated GIL cannot monitor the internal state of the device in real time, and provides a reference for the construction of digital twin of power transmission and transformation equipment and fault diagnosis and state monitoring.

[0007] Therefore, the first aspect of the present application provides a real-time online monitoring method for GIL temperature distribution, which comprises:

[0008] S1, establish a three-phase integrated GIL heat flow coupling three-dimensional simulation model, and determine the variable z affecting the overall temperature distribution of the three-phase integrated GIL, and determine the monitoring point position of the three-phase integrated GIL shell;

[0009] S2, according to the actual operation condition of the three-phase integrated GIL, determine the selection range of the variable z, obtain a set of data set Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid node;

[0010] S3, extracting the monitoring point position data in the temperature data set Y to obtain the monitoring point temperature data set Y l , extracting the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and performing dimension reduction processing on the solid domain temperature data set Y s to obtain the low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set;

[0011] S4, constructing the implicit nonlinear relationship between the monitoring point temperature data set Y l and the low-dimensional data set D to obtain the fast calculation model of the overall temperature solid domain part of the three-phase integrated GIL, and constructing the mapping relationship between the solid domain temperature data set Y s and the temperature field data set Y to obtain the online monitoring model of the overall temperature of the three-phase integrated GIL;

[0012] S5, inputting any monitoring point temperature data Y l into the fast calculation model to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and reconstructing the overall temperature distribution of the three-phase integrated GIL through the online monitoring model.

[0013] Optionally, the variable z includes: ambient temperature, current-carrying capacity and ambient wind speed.

[0014] Optionally, obtaining a set of data set Z containing different variables z according to the selection range includes: obtaining a set of data set Z containing different variables z in the selection range through an equal interval scanning method.

[0015] Optionally, the dimension reduction processing on the solid domain temperature data set Y s includes: adopting singular value decomposition method to perform dimension reduction processing on the solid domain temperature data set Y s .

[0016] Optionally, the construction of the implicit nonlinear relationship between the monitoring point temperature data set Y lBy establishing an implicit nonlinear relationship with the low-dimensional dataset D, a fast computational model for the solid-state domain portion of the three-phase integrated GIL global temperature is obtained, and the solid-state domain temperature dataset Y is constructed. s The mapping relationship with the temperature field dataset Y yields the three-phase integrated GIL overall temperature online monitoring model, including:

[0017] The monitoring point temperature dataset Y is mapped using a first deep learning method. l After performing SVD decomposition on the low-dimensional dataset D, the resulting dataset is... The implicit nonlinear relationship between them is used to obtain a fast calculation model for the overall temperature solid domain part of the three-phase integrated GIL;

[0018] The solid-domain temperature dataset Y is mapped using a second deep learning method. s After performing SVD decomposition on the temperature field dataset Y, the solid domain temperature dataset Y is obtained. s The mapping relationship between the three-phase integrated GIL and the overall temperature dataset Y is used to obtain the overall temperature online monitoring model.

[0019] Optionally, the first deep learning method is a BP neural network.

[0020] Optionally, the second deep learning method is a deep convolutional neural network.

[0021] A second aspect of this application provides a real-time online monitoring system for GIL temperature distribution, the system comprising:

[0022] A unit is established to create a three-dimensional simulation model of the thermal-fluid coupling of the three-phase integrated GIL, determine the variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determine the location of the monitoring point on the shell of the three-phase integrated GIL.

[0023] The acquisition unit is used to determine the selection range of variable z according to the actual operating conditions of the three-phase integrated GIL, acquire a set of dataset Z containing different variables z according to the selection range, and a temperature field dataset Y corresponding to the simulation calculation, and export the dataset according to the preset grid nodes.

[0024] The extraction unit is used to extract the monitoring point location data from the temperature dataset Y to obtain the monitoring point temperature dataset Y. l The solid-domain temperature dataset Y is obtained by extracting the solid-domain temperature data from the temperature dataset Y. s And for the solid domain temperature dataset Y s Dimensionality reduction is performed to obtain the low-dimensional dataset D corresponding to the high-dimensional solid-domain temperature dataset;

[0025] Construction unit, used to construct the temperature dataset Y of the monitoring points.l obtaining a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL by the implicit nonlinear relationship with the low-dimensional data set D, and constructing the temperature data set Y of the solid domain s obtaining an online monitoring model of the overall temperature of the three-phase integrated GIL by the mapping relationship with the temperature field data set Y;

[0026] a monitoring unit configured to obtain the temperature data Y of any monitoring point l inputting the fast calculation model to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and reconstructing the overall temperature distribution of the three-phase integrated GIL through the online monitoring model.

[0027] The third aspect of the present application provides a real-time online monitoring device for GIL temperature distribution, the device comprising a processor and a memory:

[0028] The memory is configured to store program code and transmit the program code to the processor;

[0029] The processor is configured to execute the steps of the real-time online monitoring method for GIL temperature distribution according to the instructions in the program code.

[0030] The fourth aspect of the present application provides a computer readable storage medium for storing program code, the program code being used to execute the real-time online monitoring method for GIL temperature distribution.

[0031] From the above technical solutions, the present application has the following advantages:

[0032] The application provides a real-time online monitoring method for GIL temperature distribution, 1) combining data dimension reduction technology and deep learning technology, according to the known real structure and operation conditions of the three-phase integrated GIL, obtaining the implicit nonlinear mapping relationship between the high-fidelity simulation simulation result data and the GIL shell monitoring point, which can realize the real-time state monitoring of the overall temperature of the three-phase integrated GIL over the sliding contact and the thermal fault diagnosis of the sliding contact resistance. 2) The overall temperature data of the three-phase integrated GIL is separated into fluid and solid, avoiding the influence of the temperature data structure of the fluid domain on the temperature data structure characteristics of the solid domain, making the physical characteristics of the solid domain data more obvious during singular value decomposition, and facilitating the accurate construction of the nonlinear relationship between the shell monitoring point temperature and the solid domain temperature. 3) The singular value decomposition algorithm based on BP neural network is used in the solid domain, so that the temperature prediction of the solid domain is more accurate; the deep convolutional neural network is used in the fluid domain to construct the relationship between the solid domain temperature and the fluid domain temperature, which can effectively restore the overall temperature distribution of the three-phase integrated GIL over the sliding contact. Thus, the problem that the three-phase integrated GIL cannot monitor the internal state of the equipment in real time is solved, and a reference is provided for the construction of the digital twin of the power transmission and transformation equipment and the fault diagnosis and state monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0033] Fig. 1 is a flowchart of a real-time online monitoring method for GIL temperature distribution provided in the embodiment of the application;

[0034] Fig. 2 is a BP neural network structure diagram for predicting the temperature of the solid domain of the three-phase integrated GIL device provided in the embodiment of the application;

[0035] Fig. 3 is a deep convolutional neural network structure diagram for predicting the temperature of the fluid domain of the three-phase integrated GIL device provided in the embodiment of the application;

[0036] Fig. 4 is a comparison between the distribution cloud diagram of the finite element calculation of the three-phase integrated GIL device and the real-time simulation output result provided in the embodiment of the application;

[0037] Fig. 5 is an error distribution diagram of the model prediction result of the three-phase integrated GIL device and the finite element simulation result provided in the embodiment of the application;

[0038] Fig. 6 is a structure diagram of a real-time online monitoring system for GIL temperature distribution provided in the embodiment of the application. DETAILED DESCRIPTION

[0039] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0040] Referring to FIG. 1, the GIL temperature distribution real-time online monitoring method provided in the embodiments of the present application comprises:

[0041] Step 101, a three-phase integrated GIL heat-flow coupling three-dimensional simulation model is established, and a variable z affecting the overall temperature distribution of the three-phase integrated GIL is determined, and a three-phase integrated GIL shell monitoring point position is determined.

[0042] It should be noted that in an embodiment, according to the actual size requirements of the three-phase integrated GIL, a three-phase integrated GIL heat-flow coupling three-dimensional simulation model is established, a variable z affecting the overall temperature distribution of the three-phase integrated GIL is determined, and a three-phase integrated GIL shell monitoring point position is determined.

[0043] The variable z includes: ambient temperature, current-carrying capacity and ambient wind speed; the three-phase integrated GIL shell monitoring point position needs to be calculated according to the actual position of the simulation model node number in order to extract its temperature data.

[0044] Step 102, the selection range of the variable z is determined according to the actual operating conditions of the three-phase integrated GIL, a set of data set Z containing different variables z is obtained according to the selection range, and the corresponding temperature field data set Y is simulated and calculated, and the data set is exported according to the preset grid node.

[0045] It should be noted that in an embodiment, according to the actual operating conditions of the three-phase integrated GIL, the selection range of the variable z is determined, and a set of data set Z containing different variables z is obtained in the given range by equal interval scanning method Z={z1,z2,…,zN}, the corresponding temperature field data set Y is simulated and calculated Y={T1,T2,…,TN}, and is exported according to the given grid node. N} and is exported according to the given grid node.

[0046] The equal interval scanning method needs to determine the upper and lower limits of the main variable parameters according to the simulation calculation, and the variable z is sampled at equal intervals. Exporting according to the given grid node means that the temperature results under different variables z obtained by simulation calculation without changing the grid partition are the same, and each node coordinate (x, y, z) corresponds to a temperature result.

[0047] Step 103, extracting the monitoring point position data in the temperature data set Y to obtain a monitoring point temperature data set Y l ; extracting the solid domain temperature data in the temperature data set Y to obtain a solid domain temperature data set Y s , and performing dimension reduction processing on the solid domain temperature data set Y s to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set.

[0048] It should be noted that in one embodiment, the monitoring point position data in the temperature data set Y obtained in step 102 is extracted to obtain a monitoring point temperature data set Y l = {T l1 , T l2 , …, T lN}; the solid domain temperature data in the temperature data set obtained in step 102 is extracted to obtain Y s = {T s1 , T s2 , …, T sN}, and dimension reduction processing is performed to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set.

[0049] wherein the solid domain temperature data set Y s is subjected to dimension reduction processing, and the singular value decomposition method is used, and the processing process is as follows:

[0050] The SVD of the temperature matrix Y sn×m is defined as:

[0051] Y s = UΣV T ; (1)

[0052] In the formula, U is a matrix, n represents the number of grid nodes, and is the left singular vector; Σ is an n x m matrix, m represents the number of variable z cases, and is the right singular vector.

[0053] The elements on the diagonal are singular values, and the remaining elements are 0 except the elements on the diagonal; V is an m x m matrix. The singular values are arranged from large to small, and the left and right singular vectors correspond to the singular values one by one. The larger the singular value, the more the corresponding left and right singular vectors occupy the original signal energy. The first j singular values are truncated, and then The first j rows and the first j columns are taken to obtain a j x j singular matrix, and similarly According to formula (1), the original temperature data can be reconstructed by multiplication.

[0054] First, the extracted solid domain temperature data is subjected to SVD decomposition, and the specific decomposition is as follows:

[0055] Let matrix A ∈ Rm*n Then there exists an orthogonal matrix U∈R m*m and an orthogonal matrix V∈R n*n with:

[0056] A = UΣV T ; (3)

[0057] where: Σ = diag(λ1, λ2, …, λ α )(α = min(m, n)), singular values λ α satisfy λ1≥ λ2≥ …≥ λ α > 0. The column vectors of U are the eigenvectors of AA T , and the column vectors of V are the eigenvectors of A T .

[0058] According to the theory of linear algebra, equation (3) can be written in vector form:

[0059] u i is the column vector of U, and v i is the column vector of V. In order to ensure the calculation accuracy and the accuracy of the prediction model, the singular values λ i need to satisfy the following conditions:

[0060] where η r represents the proportion of the first r-order singular value to the sum of all singular values. Under the premise of meeting the calculation accuracy and without greatly increasing the calculation time, ε is selected as 99.999%. At this time, the reconstruction matrix can be written as:

[0061] Further, the above-mentioned truncation value j is determined according to the percentage of the first j singular values to the total singular values. In general, in order to ensure the calculation accuracy, the percentage of the first j singular values to the total singular values needs to reach 99.999%.

[0062] It can be understood that in order to ensure the calculation accuracy, after singular value decomposition of the matrix, the proportion of the first r-order singular value to the total energy needs to reach 99.999%. When singular value decomposition is performed on the solid domain, the energy of the first 3-order singular value reaches 99.999%, that is, the original high-order data (180097-order) is reduced to low-order data (3-order, corresponding to the temperature characteristics of three integrated GIL current carriers and the surrounding shell). However, when singular value decomposition is performed on the whole calculation domain, the energy of the first 14-order singular value reaches 99.999%, that is, the data is reduced to 14-order data. Therefore, the way of separating fluid and solid can improve the reduction efficiency of the solid domain temperature and improve the prediction accuracy, so that the physical interpretability of the network model is stronger.

[0063] Step 104, constructing the monitoring point temperature dataset Y l The implicit nonlinear relationship between the low-dimensional dataset D and the solid domain part of the overall temperature of the three-phase integrated GIL is obtained, a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL is obtained, and a solid domain temperature dataset Y is constructed s The mapping relationship with the temperature field dataset Y is obtained, and an online monitoring model of the overall temperature of the three-phase integrated GIL is obtained.

[0064] It should be noted that the dataset Y l The implicit nonlinear relationship between the dataset D in step 103 and the solid domain part of the overall temperature of the three-phase integrated GIL is obtained, a fast calculation model G1 of the solid domain part of the overall temperature of the three-phase integrated GIL is obtained, and the dataset Y in step 103 is constructed s The mapping relationship with the dataset Y in step 102 is obtained, and an online monitoring model G2 of the overall temperature of the three-phase integrated GIL is obtained.

[0065] Further, in one embodiment, the BP neural network is used to map the monitoring point temperature dataset Y l After SVD decomposition of the low-dimensional dataset D, the dataset The implicit nonlinear relationship between the two is obtained, thereby obtaining a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL; the deep convolutional neural network is used to map the solid domain temperature dataset Y s After SVD decomposition of the temperature field dataset Y, the solid domain temperature dataset Y s The mapping relationship with the overall temperature dataset Y is obtained, thereby obtaining an online monitoring model of the overall temperature of the three-phase integrated GIL. The structure of the BP neural network is shown in FIG. 4, and the structure of the deep convolutional neural network is shown in FIG. 3.

[0066] It should be noted that the deep learning method, including the BP neural network, the convolutional neural network, etc., the BP neural network is used to construct the relationship between Y l and The convolutional neural network is used to construct the relationship between Y s and Y.

[0067] It can be understood that the neural network is a multi-layer feedforward neural network that corrects errors through an error backpropagation algorithm, and its structure includes an input layer, a hidden layer and an output layer, wherein each layer of the hidden layer contains multiple neurons for learning the relationship between the input and output data. The neural network is based on the classic U-Net network structure of medical image segmentation, and adopts an encoder plus decoder structure, wherein the encoder is mainly a convolutional layer for extracting the intrinsic features of the solid domain temperature data; the decoder is mainly a transposed convolutional layer for expanding the intrinsic features to the original dimension and predicting the fluid domain temperature.

[0068] Step 105, inputting the temperature data Y of the arbitrary monitoring point l The three-phase integrated GIL overall solid domain temperature distribution is obtained by inputting the fast calculation model, and the three-phase integrated GIL overall temperature distribution is reconstructed through the online monitoring model.

[0069] It should be noted that the reconstruction method, under the input of the temperature data Y of the arbitrary monitoring point , predicts the output result through the BP neural network model . The data set is reconstructed to obtain the solid domain temperature field distribution data under the temperature data Y of the monitoring point . Then, the convolutional neural network model is used to predict the overall temperature distribution data under the solid domain temperature Y.

[0070] Wherein, the distribution cloud diagram of the finite element calculation is compared with the real-time simulation output result of the application, as shown in Figure 4. The left half of Figure 4 is the finite element calculation result, and the right half is the real-time simulation calculation result of the application. The error distribution diagram of the device model prediction result and the finite element simulation result is shown in Figure 5.

[0071] The real-time online monitoring method of GIL temperature distribution provided in the embodiment of the application, 1) combines data dimension reduction technology and deep learning technology, and obtains the implicit nonlinear mapping relationship between high-fidelity simulation simulation result data and GIL shell monitoring points according to the known real structure and operating conditions of the three-phase integrated GIL, which can realize real-time state monitoring of the overall temperature of the three-phase integrated GIL over the sliding contact and thermal fault diagnosis of the sliding contact contact resistance. 2) The fluid-solid separation is performed on the overall temperature data of the three-phase integrated GIL, which avoids the influence of the temperature data structure of the fluid domain on the temperature data structure characteristics of the solid domain, makes the physical characteristics of the solid domain data more obvious during singular value decomposition, and facilitates accurate construction of the nonlinear relationship between the shell monitoring point temperature and the solid domain temperature. 3) The singular value decomposition algorithm based on BP neural network is used in the solid domain, so that the temperature prediction of the solid domain is more accurate; the deep convolutional neural network is used in the fluid domain to construct the relationship between the solid domain temperature and the fluid domain temperature, which can effectively restore the overall temperature distribution of the three-phase integrated GIL over the sliding contact. Thus, the problem that the three-phase integrated GIL cannot monitor the internal state of the device in real time is solved, which provides a reference for the construction of digital twin of power transmission and transformation equipment and fault diagnosis and state monitoring.

[0072] The above is a real-time online monitoring method of GIL temperature distribution provided in the embodiment of the application, and the following is a real-time online monitoring system of GIL temperature distribution provided in the embodiment of the application.

[0073] ​Referring to FIG. 6, the GIL temperature distribution real-time online monitoring system provided in the embodiment of the present application comprises:

[0074] The establishing unit 201 is configured to establish a three-phase integrated GIL heat flow coupling three-dimensional simulation model, determine a variable z affecting the overall temperature distribution of the three-phase integrated GIL, and determine a monitoring point position of the three-phase integrated GIL shell.

[0075] The acquiring unit 202 is configured to determine a selection range of the variable z according to an actual operation condition of the three-phase integrated GIL, acquire a set of data Z containing different variables z according to the selection range, simulate and calculate a temperature field data Y corresponding to the data set, and export the data set according to a preset grid node.

[0076] The extracting unit 203 is configured to extract the monitoring point position data in the temperature data set Y to obtain a monitoring point temperature data set Y l , extract the solid domain temperature data in the temperature data set Y to obtain a solid domain temperature data set Y s , and perform dimension reduction processing on the solid domain temperature data set Y s to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set.

[0077] The constructing unit 204 is configured to construct an implicit nonlinear relationship between the monitoring point temperature data set Y l and the low-dimensional data set D to obtain a fast calculation model of the overall temperature solid domain part of the three-phase integrated GIL, and construct a mapping relationship between the solid domain temperature data set Y s and the temperature field data set Y to obtain an overall temperature online monitoring model of the three-phase integrated GIL.

[0078] The monitoring unit 205 is configured to input the arbitrary monitoring point temperature data Y l into the fast calculation model to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and reconstruct the overall temperature distribution of the three-phase integrated GIL through the online monitoring model.

[0079] Further, the embodiment of the present application further provides a GIL temperature distribution real-time online monitoring device, which comprises a processor and a memory:

[0080] The memory is configured to store program code and transmit the program code to the processor.

[0081] The processor is configured to execute the steps of the GIL temperature distribution real-time online monitoring method according to the instructions in the program code.

[0082] Further, the embodiment of the present application further provides a computer readable storage medium for storing program codes, the program codes being used for executing the real-time online monitoring method of GIL temperature distribution.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0084] The terms "first", "second", "third", "fourth" and the like used in the description of the specification and the above drawings, if any, are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0085] It should be understood that in the present application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the association between the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0086] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. The division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0087] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0088] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0089] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), a random access memory (English full name: Random Access Memory, English abbreviation: RAM), a magnetic disk or an optical disk, and various program code storage media.

[0090] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for real-time online monitoring of GIL temperature distribution, characterized in that, The method comprises the following steps: S1, establishing a three-phase integrated GIL heat flow coupling three-dimensional simulation model, determining a variable z affecting the overall temperature distribution of the three-phase integrated GIL, and determining the location of a monitoring point of the outer shell of the three-phase integrated GIL; S2, determining the selection range of the variable z according to the actual operating condition of the three-phase integrated GIL, obtaining a data set Z containing different variables z according to the selection range, simulating and calculating a temperature field data set Y corresponding thereto, and exporting the data set according to a preset grid node; S3, extracting the monitoring point position data in the temperature data set Y to obtain a monitoring point temperature data set Y l ; extracting the solid domain temperature data of the temperature data set Y to obtain a solid domain temperature data set Y s , and performing dimension reduction processing on the solid domain temperature data set Y s to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set. S4, constructing the monitoring point temperature dataset Y l a fast calculation model of the solid domain part of the three-phase integrated GIL overall temperature is obtained according to the implicit nonlinear relationship with the low-dimensional dataset D, and the solid domain temperature dataset Y is constructed s an online monitoring model of the three-phase integrated GIL overall temperature is obtained according to the mapping relationship with the temperature field dataset Y; S5、obtain the temperature data Y of any monitoring point l The temperature distribution of the whole solid region of the three-phase integrated GIL is obtained by inputting the fast calculation model, and the temperature distribution of the whole three-phase integrated GIL is reconstructed through the online monitoring model.

2. The method of real-time online monitoring of GIL temperature distribution according to claim 1, characterized in that, The variable z comprises an ambient temperature, a load flow, and an ambient wind speed.

3. The method of real-time online monitoring of GIL temperature profile according to claim 1, wherein, The method comprises the following steps:

4. The method of real-time online monitoring of GIL temperature profile according to claim 1, wherein, said solid domain temperature data set Y s performing dimensionality reduction, including: applying singular value decomposition to said solid domain temperature data set Y s performing dimensionality reduction.

5. The method of real-time online monitoring of GIL temperature profile according to claim 1, wherein, The constructing the monitoring point temperature dataset Y l The implicit nonlinear relationship with the low-dimensional dataset D obtains a fast calculation model of the solid domain part of the three-phase integrated GIL overall temperature, and constructs the solid domain temperature dataset Y s The mapping relationship with the temperature field dataset Y obtains an online monitoring model of the three-phase integrated GIL overall temperature, including: mapping the monitoring point temperature dataset Y using a first deep learning method l after SVD decomposition of the low-dimensional dataset D, a dataset An implicit nonlinear relationship between the variable z and the temperature field data set Y is obtained, so as to obtain a fast calculation model of the overall temperature solid domain of the three-phase integrated GIL; mapping the solid domain temperature dataset Y using a second deep learning method s After SVD decomposition of the temperature field dataset Y, the solid domain temperature dataset Y is obtained s The mapping relationship with the overall temperature dataset Y is obtained, thereby obtaining the overall temperature online monitoring model of the three-phase integrated GIL.

6. The method of real-time online monitoring of GIL temperature profile according to claim 5, wherein, The first deep learning method is a BP neural network.

7. The method of real-time online monitoring of GIL temperature profile according to claim 5, wherein, The second deep learning method is a deep convolutional neural network.

8. A real-time online monitoring system of GIL temperature distribution, characterized in that, The method comprises the following steps: A establishing unit is configured to establish a three-phase integrated GIL heat flow coupling three-dimensional simulation model, determine a variable z affecting the overall temperature distribution of the three-phase integrated GIL, and determine the location of a monitoring point of the outer shell of the three-phase integrated GIL; A obtaining unit is configured to determine the selection range of the variable z according to the actual operating condition of the three-phase integrated GIL, obtain a data set Z containing different variables z according to the selection range, simulate and calculate a temperature field data set Y corresponding thereto, and export the data set according to a preset grid node; an extraction unit configured to extract monitoring point temperature data set Y from the monitoring point position data in the temperature data set Y l ; extract solid domain temperature data set Y from the solid domain temperature data in the temperature data set Y s , and perform dimension reduction processing on the solid domain temperature data set Y s to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set. a constructing unit configured to construct the monitoring point temperature dataset Y l a mapping relationship with the temperature field dataset Y, to obtain an online monitoring model of the overall temperature of the three-phase integrated GIL s a mapping relationship with the temperature field dataset Y, to obtain an online monitoring model of the overall temperature of the three-phase integrated GIL a monitoring unit for obtaining arbitrary monitoring point temperature data Y l inputting the fast calculation model The overall solid domain temperature distribution of the three-phase integrated GIL is determined, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

9. A device for real-time online monitoring of GIL temperature distribution, characterized in that, The device comprises a processor and a memory: The memory is configured to store program code and transmit the program code to the processor; The processor is configured to execute the real-time online monitoring method of the GIL temperature distribution according to the instructions in the program code.

10. A computer readable storage medium characterized by, The computer readable storage medium is configured to store program code for executing the real-time online monitoring method of the GIL temperature distribution.

Images